# Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation

arXiv: https://arxiv.org/abs/2511.19835 · HTML: https://mlsanity.com/paper/2511.19835/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 30 of its 33 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [Mean Flows for One-step Generative Modeling](https://mlsanity.com/paper/2505.13447/) (2025)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention](https://mlsanity.com/paper/2407.02490/) (2024)
- [DeepCache: Accelerating Diffusion Models for Free](https://mlsanity.com/paper/2312.00858/) (2023)
- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity](https://mlsanity.com/paper/2502.01776/) (2025)
- [VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation](https://mlsanity.com/paper/2412.21059/) (2024)
- [Fast Video Generation with Sliding Tile Attention](https://mlsanity.com/paper/2502.04507/) (2025)
- [Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation](https://mlsanity.com/paper/2505.18875/) (2025)
- [Training-free and Adaptive Sparse Attention for Efficient Long Video Generation](https://mlsanity.com/paper/2502.21079/) (2025)
- [Efficient softmax approximation for GPUs](https://mlsanity.com/paper/1609.04309/) (2016)
- [LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights](https://mlsanity.com/paper/2404.11936/) (2024)
- [Training-Free Efficient Video Generation via Dynamic Token Carving](https://mlsanity.com/paper/2505.16864/) (2025)
- [Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers](https://mlsanity.com/paper/2506.03065/) (2025)
- [EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models](https://mlsanity.com/paper/2401.04585/) (2024)
- [Convex Bounds on the Softmax Function with Applications to Robustness Verification](https://mlsanity.com/paper/2303.01713/) (2023)
- [K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences](https://mlsanity.com/paper/2408.14468/) (2024)
- [CacheQuant: Comprehensively Accelerated Diffusion Models](https://mlsanity.com/paper/2503.01323/) (2025)
- [Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers](https://mlsanity.com/paper/2505.14687/) (2025)
- [DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation](https://mlsanity.com/paper/2409.14307/) (2024)

## Built on by (most cited first, 5 of 5)

- [Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation](https://mlsanity.com/paper/2604.12219/) (2026)
- [Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models](https://mlsanity.com/paper/2608.18484/) (2026)
- [SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention](https://mlsanity.com/paper/2608.12780/) (2026)
- [Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training](https://mlsanity.com/paper/2610.05416/) (2026)
- [iCATS: Fast Video Generation via Interaction-Aware Sparse Attention and Timestep-Adaptive Sparsity](https://mlsanity.com/paper/2610.11302/) (2026)

## Abstract (arXiv)

Diffusion Transformers dominate video generation, but the quadratic complexity of attention computation introduces substantial latency. Attention sparsity reduces computational costs by focusing on critical tokens while ignoring non-critical tokens. However, existing methods suffer from severe performance degradation. In this paper, we revisit attention sparsity and reveal that existing methods induce systematic biases in attention allocation: (1) excessive focus on critical tokens amplifies their attention weights; (2) complete neglect of non-critical tokens causes the loss of relevant attention weights. To address these issues, we propose Rectified SpaAttn, which rectifies attention allocation with implicit full attention reference, thereby enhancing the alignment between sparse and full attention maps. Specifically: (1) for critical tokens, we show that their bias is proportional to the sparse attention weights, with the ratio governed by the amplified weights. Accordingly, we propose Isolated-Pooling Attention Reallocation, which calculates accurate rectification factors by reallocating multimodal pooled weights. (2) for non-critical tokens, recovering attention weights from the pooled query-key yields attention gains but also introduces pooling errors. Therefore, we propose Gain-Aware Pooling Rectification, which ensures that the rectified gain consistently surpasses the induced error. Moreover, we customize and integrate the Rectified SpaAttn kernel using Triton, achieving up to 3.33 and 2.08 times speedups on HunyuanVideo and Wan 2.1, respectively, while maintaining high generation quality. We release Rectified SpaAttn as open-source at https://github.com/BienLuky/Rectified-SpaAttn .